Uploaded by International Research Journal of Engineering and Technology (IRJET)


International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019
p-ISSN: 2395-0072
Rupali Mahajan, Dr Mrs S.A. Bhisikar
S. Mahajan, Dept of Electronics Engineering, Rajarshi Shahu College of Engineering, Tathawade,
Pune – 411033, India
2Professor Dr S.A.Bhisikar, Dept. of Electronics Engineering, Rajarshi Shahu College of Engineering, Tathawade,
Pune – 411033, India
---------------------------------------------------------------------***---------------------------------------------------------------------Abstract - Agriculture plays an important role in our day to
day life. It has played a key role in the development of human
civilization. India is an agricultural country and about seventy
percent of our population depends on agriculture. So the
disease detection of plants plays an important role in the
agricultural field. Majority of the plant diseases are caused by
the attack of bacteria, fungi, virus etc. If proper care is not
taken in this area, it may lead to serious effects on plants and
adversely affects the productivity and quality. To detect, the
plant diseases we need a fast automatic way. The main
approach adopted in practice for detection and identification
of plant diseases is naked eye observation through experts. The
decision making capability of an expert also depends on
his/her physical condition, such as fatigue and eye sight, work
pressure, climate etc. So this method is time consuming and
less efficient. Here, it is proposed with an idea of detecting
plant diseases using image processing. The unhealthy leaves of
plant can be detected and can be separated from healthy
leaves. This concept can be extended to detect the symptoms of
any type of plant diseases that is affected on different
horticulture crops.
environmental factors, etc. It is very important to use
technology to overcome these issues. Image processing is
one of the best solutions for detecting plant leaf disease
detection. Here, the proposed system detects the plant leaf
disease using image processing techniques with the help of
Genetic algorithm as a classifier.
First the images of different plant leaves are acquired.
Then image processing techniques are applied to the image
of plant leaf to get the necessary features and these features
are further analyzed. The block diagram below gives the
basic process involved in the system.
The step-by-step methodology is explained as below
Keywords— Image processing, Genetic algorithm
8. Classification of the disease using Genetic
India is an agricultural country. In India about 70% of the
population depends on agriculture. Plant diseases cause
significant reduction in both quality and quantity of
agricultural products. Farmers have wide range of diversity
to select suitable Fruit and Vegetable crops. However, the
cultivation of these crops for optimum yield and quality
produce is highly technical. It can be improved by the aid of
technological support. The management of perennial fruit
crops requires close monitoring especially for the
management of diseases that can affect production
significantly and subsequently the postharvest life. The
Image processing techniques used for the fast and accurate
detection of plant diseases. The steps followed by in
detection of leaf diseases are image acquisition, image
enhancement and noise removal, image segmentation,
feature extraction and disease classification.
There are many disadvantages of conventional methods of
detecting plant leaf diseases, such as more time consuming,
inaccuracy, inefficiency for larger fields, variation in results
due to personal issues such as vision of person,
© 2019, IRJET
Impact Factor value: 7.211
Image acquisition
Colour Transformation
Masking the green-pixels
Removal of masked green pixels
Obtain the useful segments
Computing the texture features using Colour CoOccurrence methodology
Fig -1: Block diagram
ISO 9001:2008 Certified Journal
Page 4244
International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019
p-ISSN: 2395-0072
2.1 Color Transformation
The RGB images are converted into Hue Saturation,
Intensity (HSI) color space representations. The purpose of
color space is to facilitate HSI (hue, saturation, intensity)
color model is a popular color model because it is based on
human perception. Hue is a color attribute that refers to the
dominant color as perceived by an observer. Saturation
refers to the relative purity or the amount of white light
added to the hue and intensity refers to the amplitude of the
light. Color spaces can be converted from one space to
another easily. After the transformation process, the H
component is taken into account for further analysis.
2.2 Masking and Removal
In this step the greenest colored pixels are identified. After
that, based on the specified threshold value that is
computed for these pixels, the mostly green pixels are
masked. The pixels with zero red, green, blue values were
completely removed.
Fig-2: HSI, Segmented image
2.3 Segmentation
The infected portion of the leaf is extracted. The infected
region is then segmented into a number of patches of equal
size. The size of the patch is chosen in such a way that the
significant information is not lost. The patch size of 32∗ 32
pixels is taken.
2.4 Computing Texture Features
Texture features like contrast, energy, local homogeneity,
and cluster shade and cluster prominence are computed for
the Hue (H) content of the image.
2.5 Classifier
Genetic algorithm is used as a classifier to find whether plant
leaf is diseased or not. Algorithm begins with a set of
solutions called population. Solutions from one population
are chosen and then used to form a new population.
Fig -3: Result
The work is done in Python. For input a fresh and diseased
database of around 1000 plant leaf images of different plants
such as potato, tomato, etc. is taken. After transforming the
image from RGB to HSI format, the image enhancement is
done. Then segmentation process is performed to get useful
segments. After that Genetic algorithm classifies the plant
leaf with disease as unhealthy plant leaf and the other leaf as
healthy leaf. The HSI image, Segmented image are displayed
in below fig.
© 2019, IRJET
Impact Factor value: 7.211
The proposed system recognizes plant leaf diseases. Speed
and accuracy are the important characteristics required for
disease detection. Genetic algorithm is used as a
classification technique to identify the plant leaf disease.
This technique helps in early and fast recognition of plant
leaf disease.
ISO 9001:2008 Certified Journal
Page 4245
International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019
p-ISSN: 2395-0072
V. Pooja, et.al, "Identification of plant leaf diseases using
image processing techniques," IEEE Technological
Innovations in ICT for Agriculture and Rural
Development (TIAR), Chennai, 2017, pp. 130-133.
V. Singh, et.al, "Detection of unhealthy region of plant
leaves using image processing and genetic
algorithm," IEEE International Conference on Advances
in Computer Engineering and Applications, Ghaziabad,
2015, pp. 1028-1032.
C. G. Dawre "A modern approach for plant leaf disease
classification which depends on leaf image processing"
International Conference on Computer Communication
and Informatics, India, 2017.
Mr. N. P. Kumbhar,et.al, ”Agricultural plant Leaf Disease
Detection Using Image Processing” International Journal
of Advanced Research in Electrical Electronics and
Instrumentation Engineering vol. 2 no. 1 January 2013.
Keri Woods. ”Genetic Algorithms: Color Image
Segmentation Literature Review”, July 24, 2007.
© 2019, IRJET
Impact Factor value: 7.211
ISO 9001:2008 Certified Journal
Page 4246